Artificial-Intelligence, Data-Driven, Comprehensive Classification of Myeloid Neoplasms Based on Genomic, Morphological and Histological Features
Lanino L, D'Amico S, Maggioni G, Al Ali N, Wang Y, Gurnari C, Gagelmann N, Bewersdorf J, Ball S, Guglielmelli P, Meggendorfer M, Hunter A, Kubasch A, Travaglino E, Campagna A, Ubezio M, Russo A, Todisco G, Tentori C, Buizza A, Sauta E, Zampini M, Riva E, Asti G, Delleani M, Ficara F, Santoro A, Sala C, Dall'Olio D, Dall'Olio L, Kewan T, Casetti I, Awada H, Xicoy B, Vucinic V, Hou H, Chou W, Yao C, Lin C, Tien H, Consagra A, Sallman D, Kern W, Bernardi M, Chiusolo P, Borin L, Voso M, Pleyer L, Palomo L, Quintela D, Jerez A, Cornejo E, Martin P, Díaz-Beyá M, Pita A, Roldan V, Suarez D, Velasco E, Calabuig M, Garcia-Manero G, Loghavi S, Platzbecker U, Sole F, Diez-Campelo M, Maciejewski J, Kröger N, Fenaux P, Fontenay M, Santini V, Haferlach T, Germing U, Padron E, Robin M, Passamonti F, Solary E, Vannucchi A, Castellani G, Zeidan A, Komrokji R, Della Porta M. Artificial-Intelligence, Data-Driven, Comprehensive Classification of Myeloid Neoplasms Based on Genomic, Morphological and Histological Features. Blood 2024, 144: 1005. DOI: 10.1182/blood-2024-204826.Peer-Reviewed Original ResearchGenomic featuresSplicing mutationBiallelic inactivationAnalysis of genomic profilesBiallelic inactivation of TP53Clinical phenotypeGene expression profilesCNV analysisMorphological featuresInactivation of TP53Myeloid neoplasmsGenomic characterizationRNAseq dataMorphological dataMutation screeningExpression profilesMutationsJAK/STATGenomic profilingGenomeHierarchical importanceHeterogeneous phenotypesIntegrated analysisPhenotypeHematological phenotypeArtificial Intelligence-Powered Digital Pathology to Improve Diagnosis and Personalized Prognostic Assessment in Patient with Myeloid Neoplasms
Asti G, Curti N, Maggioni G, Carlini G, Lanino L, Campagna A, D'Amico S, Sauta E, Delleani M, Bonometti A, Lancellotti C, Rahal D, Ubezio M, Todisco G, Tentori C, Russo A, Crespi A, Figini G, Buizza A, Riva E, Zampini M, Brindisi M, Ficara F, Crisafulli L, Ventura D, Pinocchio N, Zazzetti E, Bicchieri M, Grondelli M, Forcina Barrero A, Savevski V, Santoro A, Santini V, Sole F, Platzbecker U, Fenaux P, Diez-Campelo M, Komrokji R, Haferlach T, Kordasti S, Di Tommaso L, Zeidan A, Loghavi S, Garcia-Manero G, Castellani G, Della Porta M. Artificial Intelligence-Powered Digital Pathology to Improve Diagnosis and Personalized Prognostic Assessment in Patient with Myeloid Neoplasms. Blood 2024, 144: 3598-3598. DOI: 10.1182/blood-2024-206248.Peer-Reviewed Original ResearchLeukemia-free survivalMyeloid neoplasmsOverall survivalConcordance indexGenomic informationBone marrowPredictive of overall survivalMD Anderson Cancer CenterCell typesProportion of patientsHarrell's concordance indexSomatic gene mutationsMorphological featuresHumanitas Research HospitalGenomic dataMGG smearsPersonalized risk assessmentRUNX1 mutationsBM aspiratesClinically relevant informationClinical entityBiopsy dataMN patientsPrognostic assessmentWhole slide images